aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/bench/breakpoint.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /tools/perf/bench/breakpoint.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to '')
-rw-r--r--tools/perf/bench/breakpoint.c244
1 files changed, 244 insertions, 0 deletions
diff --git a/tools/perf/bench/breakpoint.c b/tools/perf/bench/breakpoint.c
new file mode 100644
index 000000000..41385f89f
--- /dev/null
+++ b/tools/perf/bench/breakpoint.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <subcmd/parse-options.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
+#include <linux/time64.h>
+#include <sys/syscall.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <pthread.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include "bench.h"
+#include "futex.h"
+
+struct {
+ unsigned int nbreakpoints;
+ unsigned int nparallel;
+ unsigned int nthreads;
+} thread_params = {
+ .nbreakpoints = 1,
+ .nparallel = 1,
+ .nthreads = 1,
+};
+
+static const struct option thread_options[] = {
+ OPT_UINTEGER('b', "breakpoints", &thread_params.nbreakpoints,
+ "Specify amount of breakpoints"),
+ OPT_UINTEGER('p', "parallelism", &thread_params.nparallel, "Specify amount of parallelism"),
+ OPT_UINTEGER('t', "threads", &thread_params.nthreads, "Specify amount of threads"),
+ OPT_END()
+};
+
+static const char * const thread_usage[] = {
+ "perf bench breakpoint thread <options>",
+ NULL
+};
+
+struct breakpoint {
+ int fd;
+ char watched;
+};
+
+static int breakpoint_setup(void *addr)
+{
+ struct perf_event_attr attr = { .size = 0, };
+
+ attr.type = PERF_TYPE_BREAKPOINT;
+ attr.size = sizeof(attr);
+ attr.inherit = 1;
+ attr.exclude_kernel = 1;
+ attr.exclude_hv = 1;
+ attr.bp_addr = (unsigned long)addr;
+ attr.bp_type = HW_BREAKPOINT_RW;
+ attr.bp_len = HW_BREAKPOINT_LEN_1;
+ return syscall(SYS_perf_event_open, &attr, 0, -1, -1, 0);
+}
+
+static void *passive_thread(void *arg)
+{
+ unsigned int *done = (unsigned int *)arg;
+
+ while (!__atomic_load_n(done, __ATOMIC_RELAXED))
+ futex_wait(done, 0, NULL, 0);
+ return NULL;
+}
+
+static void *active_thread(void *arg)
+{
+ unsigned int *done = (unsigned int *)arg;
+
+ while (!__atomic_load_n(done, __ATOMIC_RELAXED));
+ return NULL;
+}
+
+static void *breakpoint_thread(void *arg)
+{
+ unsigned int i, done;
+ int *repeat = (int *)arg;
+ pthread_t *threads;
+
+ threads = calloc(thread_params.nthreads, sizeof(threads[0]));
+ if (!threads)
+ exit((perror("calloc"), EXIT_FAILURE));
+
+ while (__atomic_fetch_sub(repeat, 1, __ATOMIC_RELAXED) > 0) {
+ done = 0;
+ for (i = 0; i < thread_params.nthreads; i++) {
+ if (pthread_create(&threads[i], NULL, passive_thread, &done))
+ exit((perror("pthread_create"), EXIT_FAILURE));
+ }
+ __atomic_store_n(&done, 1, __ATOMIC_RELAXED);
+ futex_wake(&done, thread_params.nthreads, 0);
+ for (i = 0; i < thread_params.nthreads; i++)
+ pthread_join(threads[i], NULL);
+ }
+ free(threads);
+ return NULL;
+}
+
+// The benchmark creates nbreakpoints inheritable breakpoints,
+// then starts nparallel threads which create and join bench_repeat batches of nthreads threads.
+int bench_breakpoint_thread(int argc, const char **argv)
+{
+ unsigned int i, result_usec;
+ int repeat = bench_repeat;
+ struct breakpoint *breakpoints;
+ pthread_t *parallel;
+ struct timeval start, stop, diff;
+
+ if (parse_options(argc, argv, thread_options, thread_usage, 0)) {
+ usage_with_options(thread_usage, thread_options);
+ exit(EXIT_FAILURE);
+ }
+ breakpoints = calloc(thread_params.nbreakpoints, sizeof(breakpoints[0]));
+ parallel = calloc(thread_params.nparallel, sizeof(parallel[0]));
+ if (!breakpoints || !parallel)
+ exit((perror("calloc"), EXIT_FAILURE));
+
+ for (i = 0; i < thread_params.nbreakpoints; i++) {
+ breakpoints[i].fd = breakpoint_setup(&breakpoints[i].watched);
+ if (breakpoints[i].fd == -1)
+ exit((perror("perf_event_open"), EXIT_FAILURE));
+ }
+ gettimeofday(&start, NULL);
+ for (i = 0; i < thread_params.nparallel; i++) {
+ if (pthread_create(&parallel[i], NULL, breakpoint_thread, &repeat))
+ exit((perror("pthread_create"), EXIT_FAILURE));
+ }
+ for (i = 0; i < thread_params.nparallel; i++)
+ pthread_join(parallel[i], NULL);
+ gettimeofday(&stop, NULL);
+ timersub(&stop, &start, &diff);
+ for (i = 0; i < thread_params.nbreakpoints; i++)
+ close(breakpoints[i].fd);
+ free(parallel);
+ free(breakpoints);
+ switch (bench_format) {
+ case BENCH_FORMAT_DEFAULT:
+ printf("# Created/joined %d threads with %d breakpoints and %d parallelism\n",
+ bench_repeat, thread_params.nbreakpoints, thread_params.nparallel);
+ printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
+ (long)diff.tv_sec, (long)(diff.tv_usec / USEC_PER_MSEC));
+ result_usec = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+ printf(" %14lf usecs/op\n",
+ (double)result_usec / bench_repeat / thread_params.nthreads);
+ printf(" %14lf usecs/op/cpu\n",
+ (double)result_usec / bench_repeat /
+ thread_params.nthreads * thread_params.nparallel);
+ break;
+ case BENCH_FORMAT_SIMPLE:
+ printf("%lu.%03lu\n", (long)diff.tv_sec, (long)(diff.tv_usec / USEC_PER_MSEC));
+ break;
+ default:
+ fprintf(stderr, "Unknown format: %d\n", bench_format);
+ exit(EXIT_FAILURE);
+ }
+ return 0;
+}
+
+struct {
+ unsigned int npassive;
+ unsigned int nactive;
+} enable_params = {
+ .nactive = 0,
+ .npassive = 0,
+};
+
+static const struct option enable_options[] = {
+ OPT_UINTEGER('p', "passive", &enable_params.npassive, "Specify amount of passive threads"),
+ OPT_UINTEGER('a', "active", &enable_params.nactive, "Specify amount of active threads"),
+ OPT_END()
+};
+
+static const char * const enable_usage[] = {
+ "perf bench breakpoint enable <options>",
+ NULL
+};
+
+// The benchmark creates an inheritable breakpoint,
+// then starts npassive threads that block and nactive threads that actively spin
+// and then disables and enables the breakpoint bench_repeat times.
+int bench_breakpoint_enable(int argc, const char **argv)
+{
+ unsigned int i, nthreads, result_usec, done = 0;
+ char watched;
+ int fd;
+ pthread_t *threads;
+ struct timeval start, stop, diff;
+
+ if (parse_options(argc, argv, enable_options, enable_usage, 0)) {
+ usage_with_options(enable_usage, enable_options);
+ exit(EXIT_FAILURE);
+ }
+ fd = breakpoint_setup(&watched);
+ if (fd == -1)
+ exit((perror("perf_event_open"), EXIT_FAILURE));
+ nthreads = enable_params.npassive + enable_params.nactive;
+ threads = calloc(nthreads, sizeof(threads[0]));
+ if (!threads)
+ exit((perror("calloc"), EXIT_FAILURE));
+
+ for (i = 0; i < nthreads; i++) {
+ if (pthread_create(&threads[i], NULL,
+ i < enable_params.npassive ? passive_thread : active_thread, &done))
+ exit((perror("pthread_create"), EXIT_FAILURE));
+ }
+ usleep(10000); // let the threads block
+ gettimeofday(&start, NULL);
+ for (i = 0; i < bench_repeat; i++) {
+ if (ioctl(fd, PERF_EVENT_IOC_DISABLE, 0))
+ exit((perror("ioctl(PERF_EVENT_IOC_DISABLE)"), EXIT_FAILURE));
+ if (ioctl(fd, PERF_EVENT_IOC_ENABLE, 0))
+ exit((perror("ioctl(PERF_EVENT_IOC_ENABLE)"), EXIT_FAILURE));
+ }
+ gettimeofday(&stop, NULL);
+ timersub(&stop, &start, &diff);
+ __atomic_store_n(&done, 1, __ATOMIC_RELAXED);
+ futex_wake(&done, enable_params.npassive, 0);
+ for (i = 0; i < nthreads; i++)
+ pthread_join(threads[i], NULL);
+ free(threads);
+ close(fd);
+ switch (bench_format) {
+ case BENCH_FORMAT_DEFAULT:
+ printf("# Enabled/disabled breakpoint %d time with %d passive and %d active threads\n",
+ bench_repeat, enable_params.npassive, enable_params.nactive);
+ printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
+ (long)diff.tv_sec, (long)(diff.tv_usec / USEC_PER_MSEC));
+ result_usec = diff.tv_sec * USEC_PER_SEC + diff.tv_usec;
+ printf(" %14lf usecs/op\n", (double)result_usec / bench_repeat);
+ break;
+ case BENCH_FORMAT_SIMPLE:
+ printf("%lu.%03lu\n", (long)diff.tv_sec, (long)(diff.tv_usec / USEC_PER_MSEC));
+ break;
+ default:
+ fprintf(stderr, "Unknown format: %d\n", bench_format);
+ exit(EXIT_FAILURE);
+ }
+ return 0;
+}